AccScience Publishing / AJWEP / Volume 19 / Issue 1 / DOI: 10.3233/AJW220007
RESEARCH ARTICLE

Evaluating the Efficiency of the Classifier Method When  Analysing the Sales Data of Agricultural Products

Yuxin Wang1 Svetlana Avdeenko2* Yuriy Shmidt3
Show Less
1 College of Innovation and Management, Suan Sunandha Rajabhat University, Bangkok, Thailand
2 Department of Agriculture and Technology of Storage of Crop Production, Don State Agrarian University, Persianovsky, Russian Federation
3 Department of Business Informatics and Economic-Mathematical Methods, Far Eastern Federal University, Vladivostok, Russian Federation
AJWEP 2022, 19(1), 41–46; https://doi.org/10.3233/AJW220007
Submitted: 2 August 2021 | Revised: 24 August 2021 | Accepted: 24 August 2021 | Published: 19 January 2022
© 2022 by the Author(s). This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution -Noncommercial 4.0 International License (CC-by the license) ( https://creativecommons.org/licenses/by-nc/4.0/ )
Abstract

Data classification as a method of input analysis is of the greatest interest and necessity for proper  distribution and quality evaluation of agricultural products. The use of classification methods allows predicting  whether a selected sample from the data set will fit into a particular class or group, which is necessary for the process  of sorting products. This study presents the results of a comparative analysis of high-performance classifiers for  assessing the effectiveness of further use in the sorting of agricultural products. The study was carried out utilising  the classifiers of k-nearest neighbours, naive Bayesian classifiers, and artificial neural networks for data analysis  during apple fruit sorting. It has been established that the greatest accuracy 99% of the results is demonstrated  by the classifiers of k-nearest neighbours, but, at the same time, they show the lowest calculation speed (0.47 s).  The best performance at any data size (65-100%) is shown by the neural network. A comprehensive review of  the features and restrictions of the studied classification algorithms, as well as their applications in various areas  of agriculture, has been performed.

Keywords
Artificial neural network
classifier of k-nearest neighbours
intelligent data analysis
naive Bayesian classifier
Conflict of interest
The authors declare they have no competing interests.
References

Bhargava, A. and A. Bansal (2021). Fruits and vegetables  quality evaluation using computer vision: A review. Journal  of King Saud University-Computer and Information  Sciences, 33(3): 243-257.

Bhavsar, H. and A. Ganatra (2012). A comparative study  of training algorithms for supervised machine learning.  International Journal of Soft Computing and Engineering  (IJSCE), 2(4): 2231-2307.

Chao, K., Chen, Y.R., Hruschka, W.R. and F.B. Gwozdz  (2002). On-line inspection of poultry carcasses by a  dual-camera system. Journal of Food Engineering, 51(3):  185-192.

Dale, A.I. (2012). A history of inverse probability: From  Thomas Bayes to Karl Pearson. Springer Science &  Business Media.

Duda, R.O., Hart, P.E. and D.G. Stork (2012). Pattern  classification. John Wiley & Sons.

Fan, S., Li, J., Zhang, Y., Tian, X., Wang, Q., He, X., Zhang,  C. and W. Huang (2020). On line detection of defective  apples using computer vision system combined with  deep learning methods. Journal of Food Engineering,  286:110102.

Findawati, Y., Astutik, I.I., Fitroni, A.S. Indrawati, I. and N.  Yuniasih (2019). Comparative analysis of Naïve Bayes, KNearest Neighbor and C. 45 method in weather forecast.  Journal of Physics: Conference Series, 1402(6): 066046. 

Gonzalez-Fernandez, I., Iglesias-Otero, M.A., Esteki, M.,  Moldes, O.A., Mejutoand J.C. and J. Simal-Gandara  (2019). A critical review on the use of artificial neural  networks in olive oil production, characterization and  authentication. Critical Reviews in Food Science and  Nutrition, 59(12): 1913-1926.

Hemmatian, F. and M.K. Sohrabi (2019). A survey on  classification techniques for opinion mining and sentiment  analysis. Artificial Intelligence Review, 52(3): 1495-1545.

Ireri, D., Belal, E., Okinda, C., Makangeand, N. and C. Ji  (2019). A computer vision system for defect discrimination  and grading in tomatoes using machine learning and image  processing. Artificial Intelligence in Agriculture, 2: 28-37.

Karthikeya, H.K., Sudarshanand, K. and D.S. Shetty (2020).  Prediction of agricultural crops using KNN algorithm.  International Journal of Innovative Science and Research  Technology, 5(5): 1422-1424.

Kim, S., Parhi, P., Junand, H. and J. Lee (2018). Evaluation  of drought severity with a Bayesian network analysis of  multiple drought indices. Journal of Water Resources  Planning and Management, 144(1): 05017016.

Kujawa, S. and G. Niedbała (2021). Artificial neural networks in agriculture. Agriculture, 11(6): 497.

MacDonald, J.M. (2020). Tracking the consolidation of US  agriculture. Applied Economic Perspectives and Policy,  42(3): 361-379.

Marchant, J.A. and C.M. Onyango (2003). Comparison  of a Bayesian classifier with a multilayer feed-forward  neural network using the example of plant/weed/soil  discrimination. Computers and Electronics in Agriculture,  39(1): 3-22.

Moldes, O.A., Mejuto, J.C., Rial-Otero, R. and J. SimalGandara (2017). A critical review on the applications  of artificial neural networks in winemaking technology.  Critical Reviews in Food Science and Nutrition, 57(13):  2896-2908.

Narendra, V.G., Prasad, G.S. and A.J. Pinto (2020). A  framework for quality evaluation of edible nuts using  computer vision and soft computing techniques. In: International Conference on Harmony Search Algorithm.  Springer, Singapore, pp. 339-348.

Pandey, A. and A. Jain (2017). Comparative analysis of  KNN algorithm using various normalization techniques.  International Journal of Computer Network and  Information Security, 11(11): 36-42.

Prabhakar, C.J. and S.H. Mohana (2018). Computer vision  based technique for surface defect detection of apples. In: Computer Vision: Concepts, Methodologies, Tools, and  Applications. IGI Global, pp. 1627-1639.

Rajesh, P. and M. Karthikeyan (2017). A comparative study of  data mining algorithms for decision tree approaches using  weka tool. Advances in Natural and Applied Sciences,  11(9): 230-243.

Safonov, V. (2020). Assessment of heavy metals in milk  produced by black-and-white holstein cows from Moscow.  Current Research in Nutrition and Food Science Journal,  8(2): 410-415.

Safonov, V.A., Danilova, V.N.,. Ermakov, V.V. and V.I.  Vorobyov (2019). Mercury and methylmercury in surface  waters of arid and humid regions, and the role of humic  acids in mercury migration. Periodico Tche Quimica,  16(31): 892-902.

Safonov, V.A., Ermakov, V.V., Degtyarev, A.P. and N.N.  Dogadkin (2020). Prospects of biogeochemical method  implementation in identifying rhenium anomalies. IOP  Conference Series: Earth and Environmental Science,  421(6): 062035.

Utelbaeva, A.B., Ermakhanov, M.N., Zhanabai, N.Z.,  Utelbaevand, B.T. and A.A. MelDeshov (2013).  Hydrogenation of benzene in the presence of ruthenium  on a modified montmorillonite support. Russian Journal  of Physical Chemistry A, 87(9): 1478-1481.

Vaishnnave, M.P., Devi, K.S., Srinivasanand, P. and G.A.P.  Jothi (2019). Detection and classification of groundnut leaf  diseases using KNN classifier. In: 2019 IEEE International  Conference on System, Computation, Automation and  Networking (ICSCAN). IEEE, pp. 1-5.

Zhou, L., Zhang, C., Liu, F., Qiuand, Z. and Y. He  (2019). Application of deep learning in food: A review.  Comprehensive Reviews in Food Science and Food Safety,  18(6): 1793-1811.

Share
Back to top
Asian Journal of Water, Environment and Pollution, Electronic ISSN: 1875-8568 Print ISSN: 0972-9860, Published by AccScience Publishing